• 전자공학회논문지 IE
• /
• v.44 no.2
• /
• pp.41-46
• /
• 2007

In this paper, we have proposed Station Safety Management System to protect station accident. we establish a sensor part near an underground rail. If a passenger approaches an underground rail, at first, lamp is shining and warning sound is ringing. nevertheless he approaches end of underground rail, At the same time, lamp is shining, warning sound is ringing, this information transfer server and train using wireless LAN. We makes this system using low cost in comparison with another system.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.3
• /
• pp.20-26
• /
• 2020

Many children have died (Heat stroke deaths) in the U.S. after being left alone in cars during hot weather, especially summer season. According to related report, more than 800 children have died of heat stroke from being trapped in a hot car since 1998. The regulation party, government has started to make not only technical regulation to prevent tragedy but also legislate to punish. However the 75% of accident has occurred unintended by their parents. So punishment is not the best solution for this case. So in this study, we analyze the trend of regulation and technology to save occupant who remained back seat. And finally we propose a countermeasure to prevent heat stroke deaths.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.133-134
• /
• 2019

기존 택시 어플리케이션의 방식은 승객이 택시를 이용할 때 승객 근처의 택시들이 승객을 선착순으로 선택하는 방식이다. 이는 승객이 택시의 정보를 알 수 없으며 승객을 선택한 택시를 탑승해야 된다. 또 택시 관련 범죄가 지속적으로 발생하고 있으며 사회적으로 심각한 문제로 떠오르고 있다. 본 논문에서는 이를 해결하기 위하여 승객이 주변 택시들을 검색하여 선택할 수 있으며 택시의 정보를 제공 받을 수 있다. 그리고 택시 범죄를 예방하기 위해 승객이 여러 경로 중에서 원하는 경로를 선택하면 택시 기사에게 전송하여 이탈 시 감지할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.13 no.1
• /
• pp.66-75
• /
• 2010

We proposed an occupant sensing system using single video camera and ultrasonic sensor for the advanced airbag. To detect the occupant form and the face position in real-time, we used the skin color and motion information. We made the candidate face block image using the threshold value of the color difference signal corresponding to skin color and difference value of current image and previous image of luminance signal to gel motion information. And then it detects the face by the morphology and the labeling. In case of night without color and luminance information, it detects the face by using the threshold value of the luminance signal get by infra-red LED instead of the color difference signal. To evaluate the performance of the proposed occupant detection system, it performed various experiments through the setting of the IEEE camera, ultrasonic sensor, and infra-red LED in vehicle jig.

• Journal of the Korean Society for Railway
• /
• v.14 no.4
• /
• pp.341-347
• /
• 2011

In this paper, studied was the application of IT and sensor technology to trains in order to provide safety and convenience for passengers. One of applications is Lavatory Emergency Detection System in a train. Since a lavatory in a train is securely separated space, it is hard to notice an emergency inside of it unless a user sends a request for help. A system that can detect an emergency by using sensors was presented. System requirements were analyzed to design and implement a system. Prototype of the system was made. Then, tests in a laboratory were carried out based on a set of test plan to verify the system functions. Performance was turned out to be very successful. The system developed may have a chance to be installed according to the requirements of specifications of the train to be ordered.

• Journal of Korean Society of Transportation
• /
• v.18 no.3
• /
• pp.43-54
• /
• 2000

이 연구는 버스정보 시스템 설계에 필요한 운행시격 결정과 통행시간 예측을 위한 알고리즘 개발을 다룬다. 운행시격 결정 문제는 버스와 같은 대중교통 수단을 운영하는데 중요한 요소 중에 하나이다. 기존 연구는 버스 운행비용과 승객비용의 합을 최소로 하는 운행시 격을 찾는데 초점을 두고 이다. 이때 승객비용이란 승객 대기비용과 승객 교통비용의 합으로 이루어진다. 그런데 우리나라와 같이 버스회사 수입이 전액 운행수입에만 의존하는 경우엔 이러한 접근 방식이 타당하지 않다. 기존의 방식과 다르게 승객비용으로 승객 이탈비용을 사용하여 버스의 최적 운행시 격을 구하는 것이 이 연구의 목적이다. 먼저 정류장이 하나인 경우에 대해 해석적 방법으로 풀고, 정류장이 여러 개인 경우에 대해서는 시뮬레이션 기법을 적용한다. 또한 이 연구는 신뢰성이 높고 정확한 통행시간 예측정보를 산출하기 위해 2 단계 예측 기법과 전문가시스템을 이용하는 자료융합 알고리즘을 개발한다. 정확한 정보를 제공하려면 교통정보 수집원을 통해 얻는 자료가 정확해야 하고, 또한 교통상황 변화에 따라 실시간으로 통행시간을 예측하는 것이 필요하다. 이 연구는 AVL(Automatic Vehicle Location)시스템을 이용한 버스정보시스템에서 실시간 데이터와 과거 데이터를 융합하여 통행시간을 예측하는 알고리즘을 개발한다. AVL 데이터를 수집하는 과정에서는 경제성을 고려하여 데이터를 수집한다. 그리고, 버스의 운행관리와 정확한 도착예정시간을 예측하기 위해 AVL시스템을 통해 얻은 데이터의 패턴을 분석하고 유고상황을 감지한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.475-477
• /
• 2001

본 논문에서는 버스에 설치되어 있는 비디오 카메라의 연속된 승차 영상과 추출해둔 배경 영상간의 영상차 분석을 통해 승객이 특정 구역을 통과하는 것을 감지하여 계수하는 방법을 연구하였다. 배경 영상은 운행 시와 같이 배경이 급변할 때는 연속된 두 프레임의 영상차를 이용하여 동적으로 배경 영상을 얻고 정차 시에는 배경 영상을 승차 영상과 비교하여 보정하여 주는 방법으로 최적화된 배경 영상을 얻어내었다. 본 시스템은 실제 상황에서 얻어진 비디오 영상에 적용하여 93.6%의 계수 성공률을 얻어내었다.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.733-746
• /
• 2021

Purpose: This study was conducted for the purpose of selecting important events from among various events that may pose a risk to railway passengers. For this purpose, opinions of various railroad vehicle passengers and railway operator workers were investigated and analyzed. Method: The survey was conducted on 1,000 men and women in their 20s and 60s and 429 workers at 11 company across the country. A survey was conducted on the dangerous situations that may occur in subways, general railroads and high-speed rail vehicles targeting passengers. For railway operator workers, the questionnaire is limited to subway vehicles. Result: Among the passenger risk factors(abnormal behavior and dangerous situations) selected based on the frequency and importance of occurrence of passenger risk factors, the main risk factors are selected 'car door jamming', 'sexual harassment', 'intoxicating behavior', 'fighting' /assault', 'wandering around', and 'not wearing a mask'. Conclusion: The major risk factors affecting passengers were selected by surveying passengers and railway operators. we plan to develop a CCTV detection system with AI technology that can quickly and continuously detect the major risk factors of railway vehicles selected as a result of this study.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.11
• /
• pp.7964-7970
• /
• 2015

In enclosed areas such as railway tunnels, the heat and smoke generated by a fire can pose a tremendous risk to the life of passengers. To prevent or mitigate such scenarios, fire detectors are installed for early fire detection. This numerical study is preformed for establishing the method of detecting performance of fire detectors installed on railway tunnels. Numerical analysis are conducted using the fire dynamics simulator, developed by the NIST. The temperature of the tunnel walls is determined using the assumed exterior structure of the tunnel. In addition, the detection times of detectors installed at different locations in the tunnel are obtained for different sizes of the fire source, and the results are compared and analyzed.

• Journal of Korean Society of Disaster and Security
• /
• v.7 no.2
• /
• pp.35-41
• /
• 2014

If a disaster occurs in the underground like subway, disaster response system should minimize the casualties. It must quickly guide passengers to a safe evacuation route. But sometimes the system does not work properly. And then they need distributed disaster response system which make decision autonomously. We perform conceptual research about distributed autonomous decision-making disaster detection and response system and disaster detection method.